skills.rest
The-Focus-AI
The-Focus-AIOFFICIAL
Explore all skills by this author →
WebsiteGitHub

firecrawl-scrape

Extract clean markdown from URLs including JavaScript-rendered single-page applications.

Updated Jul 16, 2026
Search Tags:#firecrawl#web scraping#content extraction#url scraping#markdown extraction#spa rendering
One-click install
npx skills add https://github.com/The-Focus-AI/walking-thoughts --skill firecrawl-scrape-the-focus-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl-scrape
Source: https://github.com/The-Focus-AI/walking-thoughts/tree/main/.agents/skills/firecrawl-scrape
Command: npx skills add https://github.com/The-Focus-AI/walking-thoughts --skill firecrawl-scrape-the-focus-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Web pages often contain navigation clutter, require JavaScript rendering, or return raw HTML that is hard to use. This Skill converts any URL into clean, LLM-optimized markdown so you can read, search, and reason over page content without manual cleanup. ## Core Features & Use Cases - Markdown Extraction: Scrape one or many URLs concurrently into clean markdown files, with options to strip nav, footer, and sidebar via --only-main-content. - JavaScript Rendering: Handle JS-rendered SPAs by waiting for page rendering with --wait-for before extraction. - Flexible Output Formats: Return markdown, HTML, links, screenshots, or JSON, and optionally ask a targeted question about the page with --query. - Use Case: You need the content of a product pricing page built as a React SPA. Scrape it with a render wait, save the markdown to .firecrawl/, then grep or read the file to find the enterprise plan price. ## Quick Start Scrape the URL I provide into clean markdown and save it to a file so we can review the page content together.

Frequently Asked Questions about firecrawl-scrape

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I scrape a webpage into clean markdown?▼

Run firecrawl scrape with the URL and an output path, for example saving to .firecrawl/page.md. Add --only-main-content to strip navigation, footers, and sidebars so only the main article content is returned.

How to scrape JavaScript-rendered SPA pages?▼

Use the --wait-for option with a millisecond delay so the page finishes rendering before extraction, for example --wait-for 3000. Firecrawl handles JS-rendered single-page applications that plain HTTP fetchers cannot read.

Can I scrape multiple URLs at once with firecrawl?▼

Yes, pass several URLs to a single firecrawl scrape command and they are processed concurrently, with each result saved to the .firecrawl directory. Check firecrawl --status to see your account's concurrency limit.

When should I use scrape instead of interact or crawl?▼

Use scrape when you have a specific URL and only need its content, whether static or JS-rendered. Escalate to interact only when you need clicks, form fills, or pagination, and use crawl or map when you need to discover pages across a whole site.

Why does my scrape output JSON instead of markdown?▼

Requesting multiple formats such as --format markdown,links causes firecrawl to return a JSON object containing each format. A single format outputs raw content directly, so request only markdown if you want a plain markdown file.

Related Skills

Explore More Software Engineering Skills→
robomotioniorobomotionio
2

tavily

Automate web search, content extraction, and site mapping with Tavily.

Official
Advanced
akillnessakillness
40

llm-wiki

Build and maintain a persistent markdown wiki from immutable raw sources.

Community
Advanced
ncsound919ncsound919

web-reader

Extract structured content and metadata from web pages via page_reader.

Community
Intermediate
sharkitect-solutionssharkitect-solutions

firecrawl

Automate web scraping, crawling, and browser interactions via the Firecrawl CLI.

Community
Advanced